"2026-02-16T00:43:28.735787+00:00"2/16/2026, 12:43:28 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
329
moderation_latency
(null)
generation_time
2602
tokens_prompt
2677
tokens_completion
621
native_tokens_prompt
2484
native_tokens_completion
640
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0023452
router
(null)
provider_responses
0
status
200
is_byok
false
latency
329
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
provider_name
"Google AI Studio"
model_permaslug
"google/gemini-2.5-flash"
api_type
"completions"
id
"gen-1771202605-rHwKZRU6880e9cOTKwUY"
upstream_id
(null)
total_cost
0.0023452
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
88.8889%
Accuracy (recall)
Matched: 9/9, FP: 2
parsedCount
11
matched
9
total
9
falsePositives
2
expectedDetails
0
expected
entry
"854"
detail
"signColor"
summary
"The Raven's Nest has a green neon sign per codex, but the passage says red."
status
"matched"
matchedBy
entry
"854"
detail
"signColor"
explanation
"The codex states the sign is green neon, but the text says red."
paragraph
1
substring
"red neon sign — a stylized raven in flight"
location
extractedText
"red neon sign — a stylized raven in flight"
inBounds
true
expectedText
"The bar's red neon sign"
locationAccurate
true
1
expected
entry
"4413"
detail
"beard"
summary
"Silas's beard matches his grey-streaked auburn hair per codex, but the passage says dark brown beard."
status
"matched"
matchedBy
entry
"4413"
detail
"beard"
explanation
"The codex states Silas's beard is grey-streaked auburn, but the text says dark brown."
paragraph
3
substring
"dark brown beard"
location
extractedText
"dark brown beard"
inBounds
true
expectedText
"his dark brown beard had been freshly trimmed"
locationAccurate
true
2
expected
entry
"4413"
detail
"signetRing"
summary
"Silas wears his signet ring on his right hand per codex, but the passage says left hand."
status
"matched"
matchedBy
entry
"4413"
detail
"signetRing"
explanation
"The codex states Silas wears the signet ring on his right hand, but the text says left."
paragraph
3
substring
"on his left hand"
location
extractedText
"on his left hand"
inBounds
true
expectedText
"The silver signet ring on his left hand"
locationAccurate
true
3
expected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per codex, but the passage says golden chain."
status
"matched"
matchedBy
entry
"2001"
detail
"chainMaterial"
explanation
"The codex states the Heartstone Pendant has a silver chain, but the text says golden."
paragraph
5
substring
"The golden chain pooled around the crimson stone"
location
extractedText
"The golden chain pooled around the crimson stone"
inBounds
true
expectedText
"The golden chain pooled around the crimson stone"
locationAccurate
true
4
expected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but Rory refers to it as Prince Mammon's territory."
status
"matched"
matchedBy
entry
"853"
detail
"ruler"
explanation
"The codex states the ruler of Dymas is Prince Belphegor, but the text refers to Prince Mammon."
paragraph
5
substring
"Prince Mammon's territory"
location
extractedText
"Prince Mammon's territory"
inBounds
true
expectedText
"Prince Mammon's territory"
locationAccurate
true
5
expected
entry
"6001"
detail
"foundingYear"
summary
"The Wardens were founded in 1215 per codex, but Rory thinks 1066."
status
"matched"
matchedBy
entry
"6001"
detail
"foundingYear"
explanation
"The codex states the Wardens were founded in 1215, but the text says 1066."
paragraph
7
substring
"Their founding in 1066"
location
extractedText
"Their founding in 1066"
inBounds
true
expectedText
"Their founding in 1066"
locationAccurate
true
6
expected
entry
"4413"
detail
"limp"
summary
"Silas limps on his left leg per codex, but the passage says right leg."
status
"matched"
matchedBy
entry
"4413"
detail
"limp"
explanation
"The codex states Silas has a limp in his left leg, but the text says he favors his right leg."
paragraph
8
substring
"favoring his right leg"
location
extractedText
"favoring his right leg"
inBounds
true
expectedText
"favoring his right leg"
locationAccurate
true
7
expected
entry
"7001"
detail
"solsticeEffect"
summary
"The Veil weakens during the winter solstice per codex, but the passage says summer solstice."
status
"matched"
matchedBy
entry
"7001"
detail
"solsticeEffect"
explanation
"The codex states the Veil strengthens during the summer solstice, but the text implies it weakens or causes spiking rift activity, which is contradictory to strengthening."
paragraph
8
substring
"The summer solstice is three days away, and the rift activity is spiking."
location
extractedText
"The summer solstice is three days away, and the rift activity is spiking."
inBounds
true
expectedText
"The summer solstice is three days away, and the rift activity is spiking"
locationAccurate
true
8
expected
entry
"4412"
detail
"scar"
summary
"Aurora's crescent scar is on her left wrist per codex, but the passage says right wrist."
status
"matched"
matchedBy
entry
"4412"
detail
"scar"
explanation
"The codex states Aurora has a scar on her left wrist, but the text says right. This is confirmed by paragraph 9, where it describes the object."
paragraph
9
substring
"crescent-shaped scar on her right wrist"
location
extractedText
"crescent-shaped scar on her right wrist"
inBounds
true
expectedText
"the crescent-shaped scar on her right wrist"
locationAccurate
true
falsePositiveDetails
0
parsed
entry
"853"
detail
"skyColor"
explanation
"The codex states the sky color of Dymas is warm amber, but the text says it turned grey."
paragraph
5
substring
"The amber sky had turned grey"
status
"false_positive"
location
extractedText
"The amber sky had turned grey"
inBounds
true
expectedText
"Prince Mammon's territory"
locationAccurate
false
closestExpected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but Rory refers to it as Prince Mammon's territory."
"The codex states the Veil strengthens during the summer solstice, but the text says it is preparing for its annual collapse at midsummer (summer solstice)."
paragraph
12
substring
"preparing for its annual collapse at the height of midsummer"
status
"false_positive"
location
extractedText
"[not found in paragraph 12]"
inBounds
true
expectedText
""
locationAccurate
false
81.8182%
Precision
True positives: 9/11
totalReported
11
truePositives
9
reportedDetails
0
parsed
entry
"854"
detail
"signColor"
explanation
"The codex states the sign is green neon, but the text says red."
paragraph
1
substring
"red neon sign — a stylized raven in flight"
status
"true_positive"
matchedExpected
entry
"854"
detail
"signColor"
summary
"The Raven's Nest has a green neon sign per codex, but the passage says red."
location
extractedText
"red neon sign — a stylized raven in flight"
inBounds
true
expectedText
"The bar's red neon sign"
locationAccurate
true
1
parsed
entry
"4413"
detail
"beard"
explanation
"The codex states Silas's beard is grey-streaked auburn, but the text says dark brown."
paragraph
3
substring
"dark brown beard"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"beard"
summary
"Silas's beard matches his grey-streaked auburn hair per codex, but the passage says dark brown beard."
location
extractedText
"dark brown beard"
inBounds
true
expectedText
"his dark brown beard had been freshly trimmed"
locationAccurate
true
2
parsed
entry
"4413"
detail
"signetRing"
explanation
"The codex states Silas wears the signet ring on his right hand, but the text says left."
paragraph
3
substring
"on his left hand"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"signetRing"
summary
"Silas wears his signet ring on his right hand per codex, but the passage says left hand."
location
extractedText
"on his left hand"
inBounds
true
expectedText
"The silver signet ring on his left hand"
locationAccurate
true
3
parsed
entry
"853"
detail
"ruler"
explanation
"The codex states the ruler of Dymas is Prince Belphegor, but the text refers to Prince Mammon."
paragraph
5
substring
"Prince Mammon's territory"
status
"true_positive"
matchedExpected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but Rory refers to it as Prince Mammon's territory."
location
extractedText
"Prince Mammon's territory"
inBounds
true
expectedText
"Prince Mammon's territory"
locationAccurate
true
4
parsed
entry
"853"
detail
"skyColor"
explanation
"The codex states the sky color of Dymas is warm amber, but the text says it turned grey."
paragraph
5
substring
"The amber sky had turned grey"
status
"false_positive"
location
extractedText
"The amber sky had turned grey"
inBounds
true
expectedText
"Prince Mammon's territory"
locationAccurate
false
closestExpected
entry
"853"
detail
"ruler"
summary
"Dymas is Prince Belphegor's realm per codex, but Rory refers to it as Prince Mammon's territory."
"The codex states the Wardens were founded in 1215, but the text says 1066."
paragraph
7
substring
"Their founding in 1066"
status
"true_positive"
matchedExpected
entry
"6001"
detail
"foundingYear"
summary
"The Wardens were founded in 1215 per codex, but Rory thinks 1066."
location
extractedText
"Their founding in 1066"
inBounds
true
expectedText
"Their founding in 1066"
locationAccurate
true
6
parsed
entry
"4413"
detail
"limp"
explanation
"The codex states Silas has a limp in his left leg, but the text says he favors his right leg."
paragraph
8
substring
"favoring his right leg"
status
"true_positive"
matchedExpected
entry
"4413"
detail
"limp"
summary
"Silas limps on his left leg per codex, but the passage says right leg."
location
extractedText
"favoring his right leg"
inBounds
true
expectedText
"favoring his right leg"
locationAccurate
true
7
parsed
entry
"7001"
detail
"solsticeEffect"
explanation
"The codex states the Veil strengthens during the summer solstice, but the text implies it weakens or causes spiking rift activity, which is contradictory to strengthening."
paragraph
8
substring
"The summer solstice is three days away, and the rift activity is spiking."
status
"true_positive"
matchedExpected
entry
"7001"
detail
"solsticeEffect"
summary
"The Veil weakens during the winter solstice per codex, but the passage says summer solstice."
location
extractedText
"The summer solstice is three days away, and the rift activity is spiking."
inBounds
true
expectedText
"The summer solstice is three days away, and the rift activity is spiking"
locationAccurate
true
8
parsed
entry
"4412"
detail
"scar"
explanation
"The codex states Aurora has a scar on her left wrist, but the text says right. This is confirmed by paragraph 9, where it describes the object."
paragraph
9
substring
"crescent-shaped scar on her right wrist"
status
"true_positive"
matchedExpected
entry
"4412"
detail
"scar"
summary
"Aurora's crescent scar is on her left wrist per codex, but the passage says right wrist."
location
extractedText
"crescent-shaped scar on her right wrist"
inBounds
true
expectedText
"the crescent-shaped scar on her right wrist"
locationAccurate
true
9
parsed
entry
"2001"
detail
"chainMaterial"
explanation
"The codex states the Heartstone Pendant has a silver chain, but the text says golden."
paragraph
5
substring
"The golden chain pooled around the crimson stone"
status
"true_positive"
matchedExpected
entry
"2001"
detail
"chainMaterial"
summary
"The Heartstone Pendant has a silver chain per codex, but the passage says golden chain."
location
extractedText
"The golden chain pooled around the crimson stone"
inBounds
true
expectedText
"The golden chain pooled around the crimson stone"
locationAccurate
true
10
parsed
entry
"7001"
detail
"solsticeEffect"
explanation
"The codex states the Veil strengthens during the summer solstice, but the text says it is preparing for its annual collapse at midsummer (summer solstice)."
paragraph
12
substring
"preparing for its annual collapse at the height of midsummer"